Topic Coverage on DBE-KT (test)
81.64AASwap
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SwapScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.03 | 81.64 | 74.48 | |
| ChatEvalScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.03 | 80.94 | 74.13 | |
| MetricsScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.03 | 80.59 | 75.17 | |
| QG-SMSScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.03 | 79.9 | 74.82 | |
| CoTScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.03 | 78.15 | 65.03 | |
| VanillaScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.03 | 74.3 | 68.89 | |
| ReferenceScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.03 | 72.55 | 66.43 | |
| QSalienceScoring Protocol=Individual Scoring2025.03 | 48.25 | — | |
| BERTScoreScoring Protocol=Individual Scoring2025.03 | 40.2 | — | |
| KDA_largeScoring Protocol=Individual Scoring2025.03 | 38.46 | — |